Standard Transformer
method
ID: standardtransformer
Related Papers
You Only Need Attention to Traverse Trees
AbstractIn recent NLP research, a topic of interest is universal sentence encoding, sentence representations that can be used in any supervised task. At the word sequence level, fully attention-based models …...
Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation
AbstractMany document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to …...
The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation
AbstractThis paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation. We focus on translating agent-side utterances from English to German. We started from an …...